@iamhenryyuan: Tested it out, and it's indeed much faster than the iPhone Mirroring + Peekaboo setup. JD.com tested fine with no issue…

X AI KOLs Timeline Tools
iphone-agent automation webdriveragent ios open-source agent-tools

Summary

作者实测并对比了两种 iPhone Agent 方案：iPhone Mirroring + Peekaboo 的视觉控制路线与基于 WebDriverAgent 的 iPhone Use，指出后者响应更快但需 iOS 开发签名环境，适合高频繁琐任务的自动化。

Tested it out, and it's indeed much faster than the iPhone Mirroring + Peekaboo setup. JD.com tested fine with no issues, but Taobao directly logged me out and even triggered slider verification, so I didn't dare to continue testing. Currently, iPhone Agent mainly follows two routes: one is using iPhone Mirroring + Peekaboo for visual control, which requires a Mac and iPhone to be logged into the same Apple ID; the other is the WebDriverAgent (WDA) used by iPhone Use, which directly operates the real device through automation interfaces. Since it's not pure screenshots, the response is faster, but it requires setting up an iOS development and signing environment. For now, I'm still inclined to mix and match depending on the scenario—this project is really cool. Things like scanning the small ticket from WeChat chat records to generate an invoice, those tedious but high-frequency tasks, feel perfect to hand off to an Agent.
Original Article
View Cached Full Text

Cached at: 10/09/26, 10:35 PM

Tested it out, and it’s indeed much faster than the iPhone Mirroring + Peekaboo setup. JD.com tested fine with no issues, but Taobao directly logged me out and even triggered slider verification, so I didn’t dare to continue testing.

Currently, iPhone Agent mainly follows two routes: one is using iPhone Mirroring + Peekaboo for visual control, which requires a Mac and iPhone to be logged into the same Apple ID; the other is the WebDriverAgent (WDA) used by iPhone Use, which directly operates the real device through automation interfaces. Since it’s not pure screenshots, the response is faster, but it requires setting up an iOS development and signing environment.

For now, I’m still inclined to mix and match depending on the scenario—this project is really cool. Things like scanning the small ticket from WeChat chat records to generate an invoice, those tedious but high-frequency tasks, feel perfect to hand off to an Agent.

钟二信@zhongerxin·Oct 8: iPhone Use https://github.com/zhongerxin/iPhone-use…

Similar Articles

iphone-use

Product Hunt

iphone-use 开源工具让 AI 智能体操控真实 iPhone 屏幕（tap/type/scroll via WebDriverAgent），并提供 MCP server、HTTP API 与浏览器远程控制，即使是无 API 的应用也能被自动化。

@denziideng: No internet, no cloud, no upload — you can have a private AI Agent right on your iPhone, and the results are amazing... Many AI assistants now upload data to the cloud, causing privacy and response speed issues... There's an open-source project that runs the AI Agent locally on the iPhone, no internet required, a thoughtful personal...

X AI KOLs Timeline

PhoneClaw is an open-source project that runs the AI Agent entirely locally on the iPhone, based on models like Gemma 4 and MiniCPM-V, no internet or data upload needed. It supports on-device operations such as voice, calendar, health data, ensuring privacy and fast response.

@jinglian: Whoa, Codex can use your iPhone! Introducing: phone-harness > Automate any iOS app like a human > Native iPhone control → no API, no jailbreak > Connect once, control anytime. Set up with just one prompt. Get started right…

X AI KOLs Timeline

Introducing phone-harness, an open-source tool that uses macOS's iPhone Mirroring to let LLMs (such as Codex) automate any iOS app like a human, without needing an API or jailbreak. It uses screenshots, Vision OCR, and HID events for vision and control.